emergent-misalignment / emergent-misalignmentLinks
☆153Updated 3 months ago
Alternatives and similar repositories for emergent-misalignment
Users that are interested in emergent-misalignment are comparing it to the libraries listed below
Sorting:
- Open source interpretability artefacts for R1.☆140Updated last month
- A toolkit for describing model features and intervening on those features to steer behavior.☆185Updated 6 months ago
- Collection of evals for Inspect AI☆144Updated this week
- ☆131Updated 2 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆225Updated 8 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆181Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingface☆103Updated 3 months ago
- METR Task Standard☆148Updated 4 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆94Updated last week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆201Updated 5 months ago
- open source interpretability platform 🧠☆219Updated this week
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆173Updated this week
- Mechanistic Interpretability Visualizations using React☆253Updated 5 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- https://transformer-circuits.pub/2025/attribution-graphs/methods.html☆61Updated 2 months ago
- ☆62Updated 2 weeks ago
- ☆124Updated 6 months ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆106Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆92Updated this week
- Inference API for many LLMs and other useful tools for empirical research☆48Updated last week
- ☆43Updated 6 months ago
- Attribution-based Parameter Decomposition☆24Updated this week
- ☆111Updated 5 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆126Updated 2 years ago
- Applying SAEs for fine-grained control☆18Updated 5 months ago
- ☆76Updated last month
- ☆28Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆77Updated last year
- ☆96Updated 2 months ago